University of Cambridge > > NLIP Seminar Series > Unsupervised Domain Tuning to Improve Word Sense Disambiguation

Unsupervised Domain Tuning to Improve Word Sense Disambiguation

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Ekaterina Kochmar.

The topic of a document can prove to be useful information for word sense disambiguation since certain meanings tend to be associated with particular topics. I will discuss three techniques which improve all existing WSD algorithms we tested by establishing a sense per (Latent Dirichlet allocation based) topic, and do not require any modification to the underlying algorithm to yield a performance increase. The evaluation of three unsupervised and one supervised algorithms is carried out on the sport and finance domains.

Joint work with Mark Stevenson.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity